Robotic-Assisted Total Knee Arthroplasty Allows for Trainee Involvement and Teaching Without Lengthening Operative Time

Utilization of Machine Learning Models to More Accurately Predict Case Duration in Primary Total Joint Arthroplasty

BACKGROUND

Accurate operative scheduling is essential for the appropriation of operating room esources. We sought to implement a machine learning model to predict primary total hip arthroplasty (THA) and total knee arthroplasty (TKA) case time.

METHODS

A total of 10,590 THAs and 12,179 TKAs between July 2017 and December 2022 were retrospectively identified. Cases were chronologically divided into training, validation, and test sets. The test set cohort included 1,588 TKAs and 1,204 THAs. There were four ML algorithms developed: linear ridge regression (LR), random forest, XGBoost, and explainable boosting machine. Each model's case time estimate was compared to the scheduled estimate measured in 15-minute "wait" time blocks ("underbooking") and "excess" time blocks ("overbooking"). Surgical case time was recorded, and SHAP values were assigned to patient characteristics, surgical information, and the patient's medical condition to understand feature importance.

RESULTS

The most predictive model input was "median previous 30 procedure case times." The XGBoost model outperformed the other models in predicting both TKA and THA case times. The model reduced TKA 'excess time blocks' by 85 blocks (P < 0.001) and 'wait time blocks' by 96 blocks (P < 0.001). The model did not significantly reduce 'excess time blocks' in THA (P = 0.89) but did significantly reduce 'wait time blocks' by 134 blocks (P < 0.001). In total, the model improved TKA operative booking by 181 blocks (2,715 minutes) and THA operative booking by 138 blocks (2,070 minutes).

CONCLUSIONS

Machine learning outperformed a traditional method of scheduling total joint arthroplasty cases. The median time of the prior 30 surgical cases was the most influential on scheduling case time accuracy. As ML models improve, surgeons should consider ML utilization in case scheduling; however, prior 30 surgical cases may serve as an adequate alternative.

Evaluating Robotic-Assisted Total Knee Arthroplasty Compared to Conventional Methods: A Systematic Review of the Literature in the United States

BACKGROUND

Robotic-assisted total knee arthroplasty (rTKA) offers a new method of surgical management for advanced arthritis of the knee. The objective of this review was to evaluate the current literature evidence comparing rTKA to conventional methods (cTKA) across multiple outcome measures.

METHODS

PubMed was used to perform a review of articles that discussed outcomes of primary rTKA. Forty-four articles were selected.

RESULTS

rTKA improves surgical precision and accuracy compared with cTKA, potentially leading to better functional outcomes and fewer complications. rTKA has longer intraoperative times and higher initial costs but leads to shorter hospital stays, lower readmission rates, reduced long-term costs and less revisions. Patient-reported outcomes for rTKA indicate less postoperative pain, reduced opioid use, and improved function.

CONCLUSIONS

rTKA may provide improved outcomes compared with cTKA. More robust clinical evidence from US-based multicenter prospective propensity matched trials is needed to fully delineate the long-term benefits and limitations of rTKA.

Robotic arm-assisted versus conventional total knee arthroplasty: comparing complications, costs, and postoperative opioid use in propensity-matched cohorts

PURPOSE

Limited literature exists substantiating benefits of robotic arm-assisted total knee arthroplasty (raTKA) over conventional total knee arthroplasty (cTKA). This study compared postoperative pain, complications, and costs between patients undergoing raTKA and cTKA using large, propensity score-matched cohorts. We hypothesize that the raTKA cohort will be associated with lower pain, lower anemia, and similar cost and other complications.

METHODS

A commercially available patient database was used for this study. Patients with raTKA and cTKA were identified with current procedural terminology and international classification of diseases (ICD-9/ICD-10) codes. Exclusions and propensity score matching were applied to mitigate confounding bias. Complication rates, costs, and postoperative opioid uses were then compared between groups.

RESULTS

Compared with patients with cTKAs (n = 31,105), patients with raTKAs (n = 6,221) had less postoperative opioid use (p < 0.01), lower rates of postoperative acute renal failure (OR 0.71; p < 0.01), anemia (OR 0.75; p < 0.01), and periprosthetic joint infection (OR 0.59; p = 0.04), and lower index costs ($875 vs. $1,169, p < 0.01).

CONCLUSION

RaTKA was associated with less postoperative pain and complications compared with cTKA.

Comparing a robotic imageless second-generation system to traditional instrumentation in total knee arthroplasty: A matched cohort analysis

Introduction

Robotic-assisted total knee arthroplasty (rTKA) has gained interest from patients and surgeons alike. Robotic systems assist with gap balancing and bone cut accuracy, which can theoretically minimize post-operative pain by decreasing soft tissue damage. This study compared perioperative results, 30- and 90-day complications, patient-reported outcomes (PROs), and survivorship to all-cause revisions between patients undergoing traditional versus rTKA.

Methods

A total of 430 TKAs (215 rTKA, 215 traditional) by two fellowship trained arthroplasty surgeons were retrospectively reviewed from 2017 to 2022. All rTKAs were performed using the CORI Surgical System (Smith & Nephew, Memphis, Tennessee). Cohorts were propensity score matched by age, sex, body mass index, and American Society of Anesthesiologist classification. Blood loss, surgical times, length of stays, 30- and 90-day complications, pain scores and PROs were compared with univariable analyses. Cox regression analyses evaluated survival to all-cause revisions.

Results

Patients undergoing rTKA had a higher incidence of discharge home (86.5 %-60.0 %) (p < 0.01). There was no difference in blood loss or surgical time. rTKA pain scores were lower in-hospital mean 2 (range, 0 to 9) vs 3 (range, 0 to 9) (p = 0.02) as well as at one-year post-operatively, mean 1 (range, 0 to 7) vs 2 (range, 0 to 10) (p = 0.02). Cox hazard ratio demonstrated no difference in survival to all-cause revisions (HR 1.3; CI 0.5 to 3.7) (p = 0.64).

Conclusion

This matched cohort analysis demonstrated potential short-term benefits associated with imageless second generation rTKA including improved early post-operative pain, without compromising survivorship to all-cause revisions.

Detecting contamination events during robotic total joint arthroplasty

BACKGROUND

Robot-assisted total joint arthroplasty (robotic-TJA) has become more widespread over the last 20 years due to higher patient satisfaction and reduced complications. However, robotic TJA may have longer operative times and increased operating room traffic, which are known risk factors for contamination events. Contamination of surgical instruments may be contact- or airborne-related with documented scalpel blade contamination rates up to 9%. The robot arm is a novel instrument that comes in and out of the surgical field, so our objective was to assess whether the robot arm is a source of contamination when used in robotic TJA compared to other surgical instruments.

METHODS

This was a prospective, single-institution, single-surgeon pilot study involving 103 robotic TJAs. The robot arm was swabbed prior to incision and after closure. Pre- and postoperative control swabs were also collected from the suction tip and scalpel blade. Swabs were incubated for 24 hours on tryptic soy agar followed by inspection for growth of any contaminating bacteria.

RESULTS

A contamination event was detected in 10 cases (10%). The scalpel blade was the most common site of contamination (8%) followed by the robot arm (2%) and suction tip (0%).

DISCUSSION

Robotic TJA is contaminated with bacteria at a rate around 10%. Although the robot arm is an additional source of potential contamination, the robot arm accrues bacterial contamination infrequently compared to the scalpel blade.

CONCLUSION

Contamination of the robot arm during robotic TJA is minimal when compared to contamination of the scalpel blade.

Comprehensive review of deep learning in orthopaedics: Applications, challenges, trustworthiness, and fusion

Deep learning (DL) in orthopaedics has gained significant attention in recent years. Previous studies have shown that DL can be applied to a wide variety of orthopaedic tasks, including fracture detection, bone tumour diagnosis, implant recognition, and evaluation of osteoarthritis severity. The utilisation of DL is expected to increase, owing to its ability to present accurate diagnoses more efficiently than traditional methods in many scenarios. This reduces the time and cost of diagnosis for patients and orthopaedic surgeons. To our knowledge, no exclusive study has comprehensively reviewed all aspects of DL currently used in orthopaedic practice. This review addresses this knowledge gap using articles from Science Direct, Scopus, IEEE Xplore, and Web of Science between 2017 and 2023. The authors begin with the motivation for using DL in orthopaedics, including its ability to enhance diagnosis and treatment planning. The review then covers various applications of DL in orthopaedics, including fracture detection, detection of supraspinatus tears using MRI, osteoarthritis, prediction of types of arthroplasty implants, bone age assessment, and detection of joint-specific soft tissue disease. We also examine the challenges for implementing DL in orthopaedics, including the scarcity of data to train DL and the lack of interpretability, as well as possible solutions to these common pitfalls. Our work highlights the requirements to achieve trustworthiness in the outcomes generated by DL, including the need for accuracy, explainability, and fairness in the DL models. We pay particular attention to fusion techniques as one of the ways to increase trustworthiness, which have also been used to address the common multimodality in orthopaedics. Finally, we have reviewed the approval requirements set forth by the US Food and Drug Administration to enable the use of DL applications. As such, we aim to have this review function as a guide for researchers to develop a reliable DL application for orthopaedic tasks from scratch for use in the market.

Robots on the Stage: A Snapshot of the American Robotic Total Knee Arthroplasty Market

» Computer-assisted robots aid orthopaedic surgeons in implant positioning and bony resection. Surgeons selecting a robot for their practice are faced with numerous options. This study aims to make the choice less daunting by reviewing the most commonly used Food and Drug Administration-approved robotic total knee arthroplasty platforms in the American arthroplasty market.» Modern total knee arthroplasty (TKA) robots use computer guidance to create a virtual knee model that serves as the surgeon's canvas for resection planning.» Most available robotic TKA (rTKA) systems are closed semiactive systems that restrict implant use to those of the manufacturer.» Each system has distinct imaging requirements, safety features, resection methods, and operating room footprints that will affect a surgeon's technique and practice.» Robots carry different purchase, maintenance, and equipment costs that will influence patient access across different socioeconomic groups.» Some studies show improved early patient-reported outcomes with rTKA, but long-term studies have yet to show clinical superiority over manual TKA.

Robotic Total Knee Arthroplasty: An Update

Total knee arthroplasty (TKA) is a gold standard surgical procedure to improve pain and restore function in patients affected by moderate-to-severe severe gonarthrosis refractory to conservative treatments. Indeed, millions of these procedures are conducted yearly worldwide, with their number expected to increase in an ageing and more demanding population. Despite the progress that has been made in optimizing surgical techniques, prosthetic designs, and durability, up to 20% of patients are dissatisfied by the procedure or still report knee pain. From this perspective, the introduction of robotic TKA (R-TKA) in the late 1990s represented a valuable instrument in performing more accurate bone cuts and improving clinical outcomes. On the other hand, prolonged operative time, increased complications, and high costs of the devices slow down the diffusion of R-TKA. The advent of newer technological devices, including those using navigation systems, has made robotic surgery in the operatory room more common since the last decade. At present, many different robots are available, representing promising solutions to avoid persistent knee pain after TKA. We hereby describe their functionality, analyze potential benefits, and hint at future perspectives in this promising field.

An evaluation of factors influencing the adoption and usage of robotic surgery in lower limb arthroplasty amongst orthopaedic trainees: a clinical survey

BACKGROUND

The rise of robotics in orthopaedic training, driven by the demand for better training outcomes and patient care, presents specific challenges for junior trainees due to its novelty and steep learning curve. This paper explores how orthopaedic trainees perceive and adopt robotic-assisted lower limb arthroplasty.

METHODS

The study utilised the UTUAT model questionnaire as the primary data collection tool, employing targeted questions on a five-point Likert scale to efficiently gather responses from a large number of participants. Data analysis was conducted using partial least squares (PLS), a well-established method in previous technology acceptance research.

RESULT

The findings indicate a favourable attitude amongst trainees towards adopting robotic technology in orthopaedic training. They acknowledge the potential advantages of improved surgical precision and patient outcomes through roboticassisted procedures. Social factors, including the views of peers and mentors, notably influence trainees' decision-making. However, the availability of resources and expert mentors did not appear to have a significant impact on trainees' intention to use robotic technology.

CONCLUSION

The study contributes to the understanding of factors influencing trainees' interest in robotic surgery and emphasises the importance of creating a supportive environment for its adoption.

Technology-Assisted Hip and Knee Arthroplasty in Orthopaedic Residency Training: A National Survey

INTRODUCTION

The adoption of technology-assisted total joint arthroplasty (TA-TJA) is increasing; however, the extent to which TA-TJA is used among orthopaedic trainees is unknown. The purpose of this study was to assess the current use of TA total knee arthroplasty (TKA) and total hip arthroplasty (THA) by orthopaedic residents and to evaluate resident perceptions toward TA-TJA in their surgical training.

METHODS

In this cross-sectional study, an anonymous electronic survey was sent to all Accreditation Council for Graduate Medical Education-accredited orthopaedic surgery residency program coordinators to distribute to their PGY-2 to PGY-5 residents. The survey consisted of 24 questions, including resident demographics, utilization of TA-TJA in their training, and perceptions regarding TA-TJA.

RESULTS

A total of 103 orthopaedic residents completed the survey, of whom 68.0% reported using TA-TJA at their institution. Of the residents using TA-TJA, 28.6% used TA for total TKA only, 71.4% used TA for both TKA and THA, and none used TA solely for THA. One-third of residents (33.3%) use TA for more than half of all TKAs conducted, whereas 57.0% use TA for <10% of all THAs conducted. Approximately half of all residents (49.5%) thought that training in TA-TJA should be required during residency, with no significant differences between junior and senior level residents ( P = 0.24). Most (82.0%) thought that trainees should be required to learn conventional TJA before learning TA-TJA. 63.0% thought that technology had a positive effect on their primary TJA training experience; however, 26.0% reported concern that their training conducting conventional TJA may be inadequate.

DISCUSSION

This study demonstrates that most orthopaedic residents currently conduct TA-TJA and highlights notable differences in TJA training experiences. These results provide a platform for future work aimed at further optimizing TJA training in residency, particularly as technology continues to rapidly evolve and utilization of TA-TJA is projected to grow exponentially.

LEVEL OF EVIDENCE

N/A, survey-based study.

Robotic-Assisted Total Knee Arthroplasty Has Similar Rates of Prosthetic Noise Generation as Conventional Total Knee Arthroplasty

Background

Noise has been reported to occur with relatively high frequency after conventional total knee arthroplasty (C-TKA), and this may impact the incidence of patient satisfaction and function. The purpose of this study was to compare the rate of patient-reported prosthetic noise generation after robotically-assisted TKA (RA-TKA) and C-TKA.

Methods

A retrospective study was conducted of unilateral primary RA-TKAs and C-TKAs performed between 2018 and 2021. Patients completed a survey consisting of 4 Likert scale questions related to prosthetic noise generation and Knee Injury and Osteoarthritis Score Joint Replacement and Forgotten Joint Score were assessed prospectively preoperatively and at a minimum of 1-year of clinical follow-up. Statistical analysis was done utilizing T-tests and chi-square tests, with statistical significance defined as a P-value < .05.

Results

One hundred sixty-two RA-TKAs and 320 C-TKAs with similar baseline characteristics and functions were included. There were no significant differences in hearing or feeling grinding, popping, clicking, or clunking (40.7% vs 38.1%; P = .647) between groups. Most RA-TKAs and C-TKAs were not dissatisfied regarding noise generation (70.4% vs 73.1%; P = .596). In both cohorts, patients who reported noise generation had lower average Forgotten Joint Scores (45.5 vs 66.1; P < .001) and lower postoperative Knee Injury and Osteoarthritis Score Joint Replacement scores (72.0 vs 81.4; P < .001) than those who did not experience noise generation.

Conclusions

While RA-TKA may facilitate soft tissue balancing, there were no differences in prosthetic noise generation between RA-TKA and C-TKA. However, those who experience implant-generated noise have lower functional outcome scores.

The Impact of Robotic-Assisted Total Knee Arthroplasty on Resident Training

BACKGROUND

As robotic-assisted total knee replacement (rTKA) continues to gain popularity, the impact of this technology on resident education remains unknown. The purpose of this study was to describe trainee experience and perceptions of rTKA and its effect on surgical training.

METHODS

Two hundred and twenty two senior orthopaedic residents attending a national board review course completed a 17-question survey regarding their experience and perceptions regarding rTKA. Mean and standard deviations were calculated for Likert scale questions, and bivariate analyses were utilized to compare answer groups.

RESULTS

Seventy percent of respondents reported exposure to rTKA during their training. Of those with robotic exposure, 20% reported that greater than half of their TKA experience involved robotics. Only 29% percent agreed that robotics improved outcomes, whereas 21% disagreed and the remainder were unsure. Over half of respondents agreed that robotics are used primarily for marketing purposes. Of those who trained with rTKA, 45% percent believed that robotics improved their understanding of the surgical procedure; however, 25% felt robotics negatively compromised their training with traditional instrumentation. Higher robotic case exposure (P = .001) and attending an industry-sponsored course (P = .02) was associated with the belief that robotics improved outcomes. Robotic case volume and percentage was associated with the belief that robotics improved understanding of the surgical procedure, however, it also was associated with reduced comfort performing traditional knee arthroplasty (P = .001).

CONCLUSION

Current resident training experience varies greatly within the United States with regards to rTKA. While exposure to rTKA may be beneficial for a well-rounded surgical education, over-exposure likely results in decreased comfort with traditional instrumentation.

A review of advances in image-guided orthopedic surgery

Orthopedic surgery remains technically demanding due to the complex anatomical structures and cumbersome surgical procedures. The introduction of image-guided orthopedic surgery (IGOS) has significantly decreased the surgical risk and improved the operation results. This review focuses on the application of recent advances in artificial intelligence (AI), deep learning (DL), augmented reality (AR) and robotics in image-guided spine surgery, joint arthroplasty, fracture reduction and bone tumor resection. For the pre-operative stage, key technologies of AI and DL based medical image segmentation, 3D visualization and surgical planning procedures are systematically reviewed. For the intra-operative stage, the development of novel image registration, surgical tool calibration and real-time navigation are reviewed. Furthermore, the combination of the surgical navigation system with AR and robotic technology is also discussed. Finally, the current issues and prospects of the IGOS system are discussed, with the goal of establishing a reference and providing guidance for surgeons, engineers, and researchers involved in the research and development of this area.

Imageless robotic-assisted total knee arthroplasty is accurate in vivo: a retrospective study to measure the postoperative bone resection and alignment

PURPOSE

Conventional instruments for total knee arthroplasty (TKA) have limited accuracy. The occurrence of outliers can negatively influence the clinical outcome and long-term survival of the implant. Orthopaedic robotic systems were developed to increase the accuracy of implant positioning and bone resections. Several systems requiring preoperative imaging have shown a higher degree of precision compared to conventional instrumentation. An imageless system needs less preoperative time and preparation and is more cost effective. Aim of this study was to find out whether this system is as precise, reproduces accurately the surgeon's planning and reduces the occurrence of outliers.

METHODS

This retrospective study included the first 71 robotic-assisted TKA and 308 conventional TKA in 374 patients. Intraoperatively planned and actual bone resections were compared. Postoperative alignment, measured on full leg weight bearing radiographs, was related to the respective planning and statistically compared between the groups.

RESULTS

Baseline characteristics (age, BMI, ASA, preoperative Knee Society Score and deformity) between both groups were comparable. According to the planned alignment, the postoperative mean difference was - 1.01° in the robotic versus 2.05° in the conventional group. The maximum deviation was - 2/+ 2.5° in the robotic and - 6.6/ + 6.8° in the conventional group. According to the plan, there were no outliers above ± 3° in the robotic versus 24% in the conventional group. The mean difference between planned and measured bone resection was 0.21 mm with a maximum of 2 mm. The 95% confidence interval was at each position 1 mm or below.

CONCLUSIONS

The described imageless robotic system is accurate in terms of coronal alignment and bone resections. In precision, it is superior to conventional instrumentation and could therefore be used to evaluate new alignment concepts.

Learning curves of robotic technology in an orthopedic teaching hospital

BACKGROUND

In recent years there has been an increasing implementation of robotic technology in arthroplasty. Due to the unclear data situation the aim of this study was to analyze the learning curve for robotic technology in residency training.

METHODS

After its introduction, the first 351 consecutive robotic knee replacements were prospectively included in the study. Surgical times, preoperative and postoperative radiographs, intraoperatively recorded alignment data and complications were analyzed. Satisfaction, revision, and referral rates were determined in a 90-day follow-up survey. Data from the last 350 navigated total knee arthroplasties were analyzed as a historical control group.

RESULTS

A learning curve of between 3 and 53 procedures was identified, depending on the surgeon, with further reductions in time measured even after 1 year of use. The operative times of the navigated technique were achieved by all surgeons. With respect to precision (alignment outliers) and patient satisfaction rate, no learning curve was evident. Comparison between tutorial and non-tutorial surgery showed a 16-min increase in operating time, but no significant differences in precision, complications, and patient satisfaction rate.

CONCLUSION

The study showed that there was a learning curve in terms of duration of surgery but not in terms of precision, complications, and patient satisfaction. Robotic tutorial surgery requires more time but provides the same outcome compared to experienced surgeons. Thus, the robotic surgical technique appears to be an excellent training tool in knee arthroplasty.